3b2ed14ae7
* refactor command manager to use docker and move to docker sdk * fix read and write actions * actually run background cmd * use bash for running cmds and fix logs * keep logs in buffer file * fix up background logs * consolidate requirements * fix docker imports * add fixme * add remove fixme * fix sandbox.py path in README * fix typo annotation and prompt --------- Co-authored-by: Xingyao Wang <xingyao6@illinois.edu>
CodeAct-based Agent Framework
This folder implements the CodeAct idea that relies on LLM to autonomously perform actions in a Bash shell. It requires more from the LLM itself: LLM needs to be capable enough to do all the stuff autonomously, instead of stuck in an infinite loop.
A minimalistic exmaple can be found at research/codeact/examples/run_flask_server_with_bash.py:
mkdir workspace
PYTHONPATH=`pwd`:$PYTHONPATH python3 opendevin/main.py -d ./workspace -c CodeActAgent -t "Please write a flask app that returns 'Hello, World\!' at the root URL, then start the app on port 5000. python3 has already been installed for you."
Example: prompts gpt-3.5-turbo-0125 to write a flask server, install flask library, and start the server.
Most of the things are working as expected, except at the end, the model did not follow the instruction to stop the interaction by outputting <execute> exit </execute> as instructed.
TODO: This should be fixable by either (1) including a complete in-context example like this, OR (2) collect some interaction data like this and fine-tune a model (like this, a more complex route).